THE NEURAL NETWORK MODEL OF INDIVIDUALS CREDIT RATING

Autores

  • Ilyas I. Ismagilov Kazan Federal University
  • Linar A. Molotov Kazan Federal University
  • Alexey S. Katasev Kazan Federal University
  • Dina V. Kataseva Kazan Federal University

DOI:

https://doi.org/10.22478/ufpb.2179-7137.2019v8n6.49308

Palavras-chave:

neural network, neural network model, borrower credit rating, modeling, data mining

Resumo

This article solves the problem of constructing and evaluating a neural network model to determine the creditworthiness of individuals. It is noted that the most important part of the modern retail market is consumer lending. Therefore, an adequate and high-quality assessment of the creditworthiness of an individual is a key aspect of providing credit to a potential borrower. The theoretical and practical aspects of assessing the creditworthiness of individuals are considered. To solve this problem, the need for the use of intelligent modeling technologies based on neural networks is being updated. The construction of a neural network model required the receipt of initial data on borrowers. Using correlation analysis, 14 input parameters were selected that most significantly affect the output. The training and test data samples were generated to build and evaluate the adequacy of the neural network model. Training and testing of the neural network model was carried out on the basis of the analytical platform “Deductor”. Analysis of contingency tables to assess the accuracy of the neural network model in the training and test samples showed positive results. The error of the first kind on the data from the training sample was 0.45%, and the error of the second kind was 1.39%. Accordingly, the error of the first kind was not observed on the data from the test sample, and the error of the second kind was 2.68%. The results obtained indicate a high generalizing ability and adequacy of the constructed neural network, as well as the possibility of its effective practical use as part of intelligent decision support systems for granting loans to potential borrowers

Downloads

Não há dados estatísticos.

Referências

Wang H., Zhong J., Zhang D., Zou X. A new classification algorithm for the bank customer credit rating // 9th International Conference on Advanced Computational Intelligence, ICACI 2017. – P. 143-148.

Abedini M., Ahmadzadeh F., Noorossana R. Customer credit scoring using a hybrid data mining approach // Kybernetes. – 2016. – No. 45(10). – P. 1576-1588.

Yi G., Lei H., Ziqiang L. Port customer credit risk prediction based on internal and external information fusion // Open Cybernetics and Systemics Journal. – 2015. – No. 9(1). – P. 1323-1328.

Li Y.-B., Zhang J.-P. Approach to multiple attribute decision making with hesitant triangular fuzzy information and their application to customer credit risk assessment // Journal of Intelligent and Fuzzy Systems. – 2014. – No. 26(6). – P. 2853-2860.

Katasev A.S., Kataseva D.V., Emaletdinova L.Yu. Neuro-fuzzy model of complex objects approximation with discrete output // Proceedings of 2nd International Conference on Industrial Engineering, Applications and Manufacturing, ICIEAM 2016.

Li B., Chai X., Zhang L., Lin T., Liu Y. Preliminary Study of Modeling and Simulation Technology Oriented to Neo-type Artificial Intelligent Systems // Journal of System Simulation. – 2018. – No. 30(2). – P. 349-362.

Das I., Roy S., Chatterjee A., Sen S. A data warehouse based schema design on decision-making in loan disbursement for Indian advance sector // Advances in Intelligent Systems and Computing. – 2019. – No. 813. – P. 603-614.

Tronnberg C.-C., Hemlin S. Lending decision making in banks: A critical incident study of loan officers // European Management Journal. – 2014. – No. 32(2). – P. 362-372.

Hashemi Taba, N., Mahfoozi Mousavi S.K., Khatavakhotan A.S. A novel algorithm developed with integrated metrics for dynamic and smart credit rating of bank customers // Lecture Notes in Electrical Engineering. – 2019. – No. 480. – P. 787-799.

Jadhav S., He H., Jenkins K. Information gain directed genetic algorithm wrapper feature selection for credit rating // Applied Soft Computing Journal. – 2018. – No. 69. – P. 541-553.

Ferreira F.A.F., Spahr R.W., Gavancha I.F.M.D., Cipi A. Readjusting trade-offs among criteria in internal ratings of credit-scoring: An empirical essay of risk analysis in mortgage loans // Journal of Business Economics and Management. – 2013. – No. 14(4). – P. 715-740.

Grunert M.L., Raker J.R., Murphy K.L., Holme T.A. Polytomous versus dichotomous scoring on multiple-choice examinations: Development of a rubric for rating partial credit // Journal of Chemical Education. – 2013. – No. 90(10). – P. 1310-1315.

Menekay M., MaAitah M.K.S. Applying expert system for bank credit authorization using fuzzy tools // ACM International Conference Proceeding Series. – 2017. – P. 258-261.

Ajili I., Ramezanpanah Z., Mallem M., Didier J.-Y. Expressive motions recognition and analysis with learning and statistical methods // Multimedia Tools and Applications. – 2019. – No. 8(12). – P. 16575-16600.

Ismagilov I.I., Khasanova S.F., Katasev A.S., Kataseva D.V. Neural network method of dynamic biometrics for detecting the substitution of computer // Journal of Advanced Research in Dynamical and Control Systems. – 2018. – No. 10(10 Special Issue). – P. 1723-1728.

Emaletdinova, L.Y., Matveev, I.V., Kabirova, A.N. Method of designing a neural controller for the automatic lateral control of unmanned aerial vehicles // Russian Aeronautics. – 2017. – No. 60(3). – P. 365-373.

Sivasankar E., Selvi C., Mala C. A study of dimensionality reduction techniques with machine learning methods for credit risk prediction // Advances in Intelligent Systems and Computing. – 2017. – No. 556. – P. 65-76.

Mustafin A.N., Katasev A.S., Akhmetvaleev A.M., Petrosyants D.G. Using models of collective neural networks for classification of the input data applying simple voting // Journal of Social Sciences Research. – 2018. – Special Issue 5. – P. 333-339.

Nagy Z., Soper D.E. Jets and threshold summation in Deductor // Physical Review D. – 2018. – No. 98(1), 014035.

Saidi R., Bouaguel W., Essoussi N. Hybrid feature selection method based on the genetic algorithm and Pearson correlation coefficient // Studies in Computational Intelligence. – 2019. – No. 801. – P. 3-24.

Prom N.A., Litvinova E.A., Shokhnekh A.V., Yovanovich T.G., Lomakin N.I. Perseptron for assessing the students' task performance in learning a foreign language according to the competencies using bi data // IOP Conference Series: Materials Science and Engineering. – 2019. – No. 483(1), 012048.

Bhardwaj S., Verma V. Improved K-means clustering algorithm using back propagation method // International Journal of Control Theory and Applications. – 2016. – No. 9(Specialissue11). – P. 5169-5180

Publicado

2019-11-27

Como Citar

I. ISMAGILOV, I. .; A. MOLOTOV, L. .; S. KATASEV, A. .; V. KATASEVA, D. . THE NEURAL NETWORK MODEL OF INDIVIDUALS CREDIT RATING. Gênero & Direito, [S. l.], v. 8, n. 6, 2019. DOI: 10.22478/ufpb.2179-7137.2019v8n6.49308. Disponível em: https://periodicos.ufpb.br/index.php/ged/article/view/49308. Acesso em: 28 mar. 2024.

Edição

Seção

Seção Livre